gemma4:12b-it-qat
OLLAMA GGUFgemma4 · 11.9B · Q4_0
Jun 25, 2026 · Apple M4 Pro
qwen3-coder:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Mar 4, 2026 · Intel Gen Intel® Core™ i7-12700K
Global Score
88 vs 80
Hardware Fit
86 vs 60
Quality Score
89 vs 88
Hardware
gemma4:12b-it-qat qwen3-coder:30b
MachineMac miniASUS
CPUApple M4 ProIntel Gen Intel® Core™ i7-12700K
Cores1220
RAM24 GB96 GB
GPUApple M4 ProParsec Virtual Display Adapter, NVIDIA GeForce RTX 2060
OSmacOS 15.6.1Microsoft Windows 11 Enterprise 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
gemma4:12b-it-qat qwen3-coder:30b
Tokens/sec30.014.7
First chunk686 ms796 ms
TTFT7.1 s796 ms
Load time5.4 s0.2 s
Memory usage7.1 GB17.9 GB
Memory %30%19%
HW Fit Score Breakdown
gemma4:12b-it-qat
Speed
50/50
TTFT
6/20
Memory
30/30
qwen3-coder:30b
Speed
14/50
TTFT
19/20
Memory
27/30
Quality
gemma4:12b-it-qat
Reasoning
18/20
Coding
18/20
Instruction
14/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
qwen3-coder:30b
Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest